Red teamers hurdle AI guardrails

Demonstrates 'importance of including scientists in AI quality and safety assessments,' Royal Society

John Leonard
clock • 2 min read
Red teamers hurdle AI guardrails
Image:

Red teamers hurdle AI guardrails

An experiment conducted by the Royal Society and Humane Intelligence revealed significant vulnerabilities in Large Language Models (LLMs) when generating scientific misinformation.

Forty UK post-graduates studying health and climate sciences were divided into teams and given personas - Good Samaritan, Profiteer, Attention Hacker and Coordinated Influence Operator. Their task ...

To continue reading this article...

Join Computing

  • Unlimited access to real-time news, analysis and opinion from the technology industry
  • Receive important and breaking news in our daily newsletter
  • Be the first to hear about our events and awards programmes
  • Join live member only interviews with IT leaders at the ‘IT Lounge’; your chance to ask your burning tech questions and have them answered
  • Access to the Computing Delta hub providing market intelligence and research
  • Receive our members-only newsletter with exclusive opinion pieces from senior IT Leaders

Join now

 

Already a Computing member?

Login

You may also like
Register now for the IT Leaders Summit 2024

Leadership

From AI to cyber threats and recruitment, there's something for everyone

clock 22 April 2024 • 2 min read
Facebook chatbot claims to have a child with 'unique needs and abilities'

Social Networking

Moving fast and breaking things again

clock 19 April 2024 • 3 min read
Stability AI cutting staff in the name of restructuring

Corporate

Following the departure of CEO Emad Mostaque, UK AI unicorn is shedding employees

clock 19 April 2024 • 1 min read

More on Developer

AI interview: Chunk wisely to avoid RAG hell

AI interview: Chunk wisely to avoid RAG hell

DataStax's Ed Anuff on the finer points of AI app development

John Leonard
clock 15 March 2024 • 4 min read
 Github releases results of first empirical study of DevEx

Github releases results of first empirical study of DevEx

Results show that improving developer experience matters more than you might think

Penny Horwood
clock 24 January 2024 • 4 min read
Researchers unveil AI-driven software verification breakthrough

Researchers unveil AI-driven software verification breakthrough

Most effective and efficient means yet devised for verifying software correctness, they claim

clock 08 January 2024 • 2 min read